© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12659
    Prev
    Next
    INDEX
    Explanations

    line break characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    際に
    -1.44
    際には
    -1.37
     zape
    -1.33
    salomon
    -1.27
     manifiesta
    -1.27
    を行い
    -1.25
    際の
    -1.23
     parecen
    -1.23
    に来て
    -1.23
     bezpiecz
    -1.22
    POSITIVE LOGITS
    。  
    1.31
    !!!!
    1.26
     как
    1.16
    新型コロナ
    1.09
     as
    1.09
    但这
    1.08
    ANTAGE
    1.07
    起伏
    1.05
     only
    1.05
    。 
    1.05
    Activations Density 0.004%

    No Known Activations